{"id":"https://openalex.org/W4403982072","doi":"https://doi.org/10.1177/02783649241273686","title":"Semantically controllable augmentations for generalizable robot learning","display_name":"Semantically controllable augmentations for generalizable robot learning","publication_year":2024,"publication_date":"2024-11-01","ids":{"openalex":"https://openalex.org/W4403982072","doi":"https://doi.org/10.1177/02783649241273686"},"language":"en","primary_location":{"id":"doi:10.1177/02783649241273686","is_oa":false,"landing_page_url":"https://doi.org/10.1177/02783649241273686","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055896639","display_name":"Zoey Qiuyu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zoey Chen","raw_affiliation_strings":["University of Washington","University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0003-4790-9107","affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101063733","display_name":"Zhao Mandi","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao Mandi","raw_affiliation_strings":["Stanford University","Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0009-0005-5877-920X","affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064794691","display_name":"Homanga Bharadhwaj","orcid":"https://orcid.org/0000-0001-5056-8516"},"institutions":[{"id":"https://openalex.org/I4210154384","display_name":"Facility for Antiproton and Ion Research","ror":"https://ror.org/053veeq82","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210154384"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Homanga Bharadhwaj","raw_affiliation_strings":["Carnegie Mellon University","FAIR","Carnegie Mellon University, Pittsburgh, PA, USA","FAIR, AI at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"FAIR","institution_ids":["https://openalex.org/I4210154384"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"FAIR, AI at Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792137","display_name":"Mohit Sharma","orcid":"https://orcid.org/0000-0002-5680-9111"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Sharma","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004644695","display_name":"Shuran Song","orcid":"https://orcid.org/0000-0002-8768-7356"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuran Song","raw_affiliation_strings":["Stanford University","Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017906439","display_name":"Abhishek Gupta","orcid":"https://orcid.org/0000-0003-1117-325X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Gupta","raw_affiliation_strings":["University of Washington","University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383672","display_name":"Vikash Kumar","orcid":"https://orcid.org/0000-0002-3168-7955"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikash Kumar","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055896639"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":0.932,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7237049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"44","issue":"10-11","first_page":"1705","last_page":"1726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6383285522460938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6269649863243103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5908886790275574},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4951426088809967},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4596002697944641},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3572317659854889}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6383285522460938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6269649863243103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5908886790275574},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4951426088809967},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4596002697944641},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3572317659854889}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/02783649241273686","is_oa":false,"landing_page_url":"https://doi.org/10.1177/02783649241273686","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2213758982","https://openalex.org/W2236233024","https://openalex.org/W2605102758","https://openalex.org/W2612690371","https://openalex.org/W2760103357","https://openalex.org/W2948672349","https://openalex.org/W2949736877","https://openalex.org/W2954996726","https://openalex.org/W2963860638","https://openalex.org/W2964198579","https://openalex.org/W2964335674","https://openalex.org/W2969018702","https://openalex.org/W2989847975","https://openalex.org/W2999905431","https://openalex.org/W3007769740","https://openalex.org/W3035756007","https://openalex.org/W3118210634","https://openalex.org/W3158545781","https://openalex.org/W3176484337","https://openalex.org/W3177021459","https://openalex.org/W3206200647","https://openalex.org/W3207832698","https://openalex.org/W4212774754","https://openalex.org/W4214570817","https://openalex.org/W4283219642","https://openalex.org/W4283788863","https://openalex.org/W4285102264","https://openalex.org/W4293527381","https://openalex.org/W4306820534","https://openalex.org/W4312933868","https://openalex.org/W4367016688","https://openalex.org/W4367721889","https://openalex.org/W4383108265","https://openalex.org/W4383108856","https://openalex.org/W4385403849","https://openalex.org/W4385430538","https://openalex.org/W4385430674","https://openalex.org/W4386065350","https://openalex.org/W4386076314","https://openalex.org/W4390873732","https://openalex.org/W4390874575","https://openalex.org/W4401416041","https://openalex.org/W6600319451","https://openalex.org/W6600612351","https://openalex.org/W6600997697","https://openalex.org/W6601158201","https://openalex.org/W6601473709","https://openalex.org/W6603946831","https://openalex.org/W6605866883","https://openalex.org/W6606157320","https://openalex.org/W6606494994","https://openalex.org/W6609435532","https://openalex.org/W6610385870","https://openalex.org/W6631455383","https://openalex.org/W6698677069"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Generalization":[0],"to":[1,10,23,30,38,100],"unseen":[2,173],"real-world":[3,18,83,105,147,174,191],"scenarios":[4,84],"for":[5,123,132,204],"robot":[6,28,139,154,160,208],"manipulation":[7,161],"requires":[8],"exposure":[9],"diverse":[11,151,190],"datasets":[12,19,140],"during":[13],"training.":[14],"However,":[15],"collecting":[16],"large":[17,63],"is":[20,36],"intractable":[21],"due":[22],"high":[24],"operational":[25],"costs.":[26],"For":[27],"learning":[29,209],"generalize":[31],"despite":[32],"these":[33],"challenges,":[34],"it":[35],"essential":[37],"leverage":[39],"sources":[40],"of":[41,65,82,153,185],"data":[42,73,124],"or":[43],"priors":[44,103],"beyond":[45,85],"the":[46,183],"robot\u2019s":[47,87],"direct":[48,88],"experience.":[49],"In":[50,111],"this":[51],"work,":[52],"we":[53,156],"posit":[54],"that":[55,96,145],"image-text":[56,186],"generative":[57,76,117,129,187,195],"models,":[58],"which":[59],"are":[60],"pre-trained":[61,116],"on":[62,150],"corpora":[64],"web-scraped":[66],"data,":[67,155],"can":[68,91,163],"serve":[69],"as":[70,119,177],"such":[71,176],"a":[72,79,86,128,199],"source.":[74],"These":[75],"models":[77,118,188],"encompass":[78],"broad":[80],"range":[81],"experience":[89],"and":[90,136,166,171,179,201],"synthesize":[92],"novel":[93],"synthetic":[94],"experiences":[95],"expose":[97],"robotic":[98,192],"agents":[99],"additional":[101],"world":[102],"aiding":[104],"generalization":[106,206],"at":[107,210],"no":[108,211],"extra":[109,212],"cost.":[110,214],"particular,":[112],"our":[113,194],"approach":[114],"leverages":[115],"an":[120],"effective":[121],"tool":[122],"augmentation.":[125],"We":[126],"propose":[127],"augmentation":[130,196],"framework":[131,197],"semantically":[133],"controllable":[134],"augmentations":[135,152],"rapidly":[137],"multiplying":[138],"while":[141],"inducing":[142],"rich":[143],"variations":[144],"enable":[146],"generalization.":[148],"Based":[149],"show":[157],"how":[158],"scalable":[159,200],"policies":[162],"be":[164],"trained":[165],"deployed":[167],"both":[168],"in":[169,172,189,207],"simulation":[170],"environments":[175],"kitchens":[178],"table-tops.":[180],"By":[181],"demonstrating":[182],"effectiveness":[184],"applications,":[193],"provides":[198],"efficient":[202],"path":[203],"boosting":[205],"human":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}